AMiner MCP Server
Enables academic paper search and analysis through the AMiner API. Supports keyword, author, and venue-based searches with advanced filtering and citation data for research assistance.
README
AMiner MCP 服务器
语言 / Language: 🇨🇳 中文 | 🇺🇸 English
基于模型上下文协议(MCP)的服务器,通过 AMiner API 提供强大的学术论文搜索和分析功能。
🌟 功能特性
🔍 搜索工具
- 关键词搜索 (
search_papers_by_keyword) - 通过关键词搜索论文 - 期刊搜索 (
search_papers_by_venue) - 搜索特定期刊/会议的论文 - 作者搜索 (
search_papers_by_author) - 搜索特定作者的论文 - 高级搜索 (
search_papers_advanced) - 多条件组合搜索
🤖 AI 助手
- 论文搜索助手 (
paper_search_assistant) - 学术研究辅助的 AI 提示模板
⚙️ 搜索选项
- 分页支持(页码、每页数量)
- 排序选项(按年份或引用数)
- 详细论文信息展示
- 专业学术格式的英文界面
🔧 MCP 客户端配置
添加到您的 MCP 客户端配置文件:
{
"mcpServers": {
"aminer": {
"command": "npx",
"args": ["-y", "@scipen/aminer-mcp-server"],
"env": {
"AMINER_API_KEY": "YOUR_AMINER_API_KEY"
}
}
}
}
🚀 手动运行
# 设置您的 AMiner API 密钥:
export AMINER_API_KEY="your_aminer_api_key_here"
# 使用 npx 启动
npx -y @scipen/aminer-mcp-server
📚 工具列表
search_papers_by_keyword
通过关键词搜索学术论文。
参数:
keyword(字符串,必需): 搜索关键词page(数字,可选): 页码,默认 0size(数字,可选): 每页论文数,默认 10,最大 10order(字符串,可选): 排序方式:'year' 或 'n_citation'
示例:
{
"keyword": "深度学习",
"page": 0,
"size": 5,
"order": "n_citation"
}
search_papers_by_venue
搜索特定期刊/会议发表的论文。
参数:
venue(字符串,必需): 期刊/会议名称page(数字,可选): 页码,默认 0size(数字,可选): 每页论文数,默认 10,最大 10order(字符串,可选): 排序方式:'year' 或 'n_citation'
示例:
{
"venue": "Nature",
"page": 0,
"size": 10,
"order": "year"
}
search_papers_by_author
搜索特定作者发表的论文。
参数:
author(字符串,必需): 作者姓名page(数字,可选): 页码,默认 0size(数字,可选): 每页论文数,默认 10,最大 10order(字符串,可选): 排序方式:'year' 或 'n_citation'
示例:
{
"author": "Geoffrey Hinton",
"page": 0,
"size": 10
}
search_papers_advanced
支持多条件的高级搜索。
参数:
keyword(字符串,可选): 搜索关键词venue(字符串,可选): 期刊/会议名称author(字符串,可选): 作者姓名page(数字,可选): 页码,默认 0size(数字,可选): 每页论文数,默认 10,最大 10order(字符串,可选): 排序方式:'year' 或 'n_citation'
注意: 必须提供 keyword、venue 或 author 中的至少一个。
示例:
{
"keyword": "自然语言处理",
"author": "Yann LeCun",
"page": 0,
"size": 5,
"order": "n_citation"
}
🎯 提示模板
paper_search_assistant
学术研究的 AI 助手提示模板。
参数:
research_topic(字符串,必需): 研究主题或领域search_focus(字符串,可选): 搜索重点recent: 关注最新论文highly_cited: 关注高引用论文comprehensive: 平衡搜索(默认)
示例:
{
"research_topic": "计算机视觉中的注意力机制",
"search_focus": "highly_cited"
}
🛠️ 开发
项目结构
src/
├── index.ts # 主服务器文件
├── aminer-client.ts # AMiner API 客户端
└── types.ts # 类型定义
可用脚本
pnpm run build- 构建项目pnpm run start- 启动服务pnpm run dev- 开发模式pnpm run lint- 代码检查pnpm test- 运行测试
技术栈
- 运行时: Node.js 18+
- 语言: TypeScript
- 框架: Model Context Protocol SDK
- 包管理器: pnpm
- API: AMiner 开放平台 API
- 协议: JSON-RPC 2.0 (MCP)
📄 许可证
MIT 许可证
🤝 贡献
欢迎提交 Issues 和 Pull Requests!
📞 支持
如有问题和支持需求, 请添加小助手的企业微信:
<img src="qrcode.jpg" alt="企业微信二维码" width="200" />
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.